Saved in:
Bibliographic Details
Main Authors: Bai, Jianchao, Jia, Linyuan, Peng, Zheng
Format: Preprint
Published: 2021
Subjects:
Online Access:https://arxiv.org/abs/2108.11125
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909647716220928
author Bai, Jianchao
Jia, Linyuan
Peng, Zheng
author_facet Bai, Jianchao
Jia, Linyuan
Peng, Zheng
contents By exploiting double-penalty terms for the primal subproblem, we develop a novel relaxed augmented Lagrangian method for solving a family of convex optimization problems subject to equality or inequality constraints. The method is then extended to solve a general multi-block separable convex optimization problem, and two related primal-dual hybrid gradient algorithms are also discussed. Convergence results about the sublinear and linear convergence rates are established by variational characterizations for both the saddle-point of the problem and the first-order optimality conditions of involved subproblems. A large number of experiments on testing the linear support vector machine problem and the robust principal component analysis problem arising from machine learning indicate that our proposed algorithms perform much better than several state-of-the-art algorithms.
format Preprint
id arxiv_https___arxiv_org_abs_2108_11125
institution arXiv
publishDate 2021
record_format arxiv
spellingShingle A new insight on augmented Lagrangian method with applications in machine learning
Bai, Jianchao
Jia, Linyuan
Peng, Zheng
Numerical Analysis
By exploiting double-penalty terms for the primal subproblem, we develop a novel relaxed augmented Lagrangian method for solving a family of convex optimization problems subject to equality or inequality constraints. The method is then extended to solve a general multi-block separable convex optimization problem, and two related primal-dual hybrid gradient algorithms are also discussed. Convergence results about the sublinear and linear convergence rates are established by variational characterizations for both the saddle-point of the problem and the first-order optimality conditions of involved subproblems. A large number of experiments on testing the linear support vector machine problem and the robust principal component analysis problem arising from machine learning indicate that our proposed algorithms perform much better than several state-of-the-art algorithms.
title A new insight on augmented Lagrangian method with applications in machine learning
topic Numerical Analysis
url https://arxiv.org/abs/2108.11125